Add GenAI OpenTelemetry-convention agent tracing

[JE-Chen]

Agent observability batch. Full layers + tests + EN/Zh v38 docs + README.

Feature (utils/agent_trace, pure-stdlib, no opentelemetry dep)

• AgentTrace records spans whose attributes follow the OpenTelemetry GenAI semantic conventions (gen_ai.operation.name, gen_ai.system, gen_ai.request.model, gen_ai.usage.input_tokens/output_tokens, gen_ai.tool.name) and the convention span name "{operation} {model}". record(...) one-shots a completed call; operation(...) is a context manager that times a live block and marks the span error on exception. summary() rolls up span/error count + token usage + duration; to_otel() exports OTLP-friendly span dicts. Clock injectable → deterministic durations.
• Pairs with trajectory evaluation (Add agent trajectory evaluation against declarative rubrics #244): record the run here, score it there.
• A module-level default_trace backs AC_trace_record / AC_trace_summary / AC_trace_export / AC_trace_reset (+ ac_*, Builder under Agent).

Verification

• 9 tests pass (GenAI attributes, summary aggregation, context-manager timing via injected clock, error marking, to_otel shape, reset, executor round-trip, wiring, facade); ruff clean; radon no CC≥C; bandit clean; PySide6-free.
• Stacked on compliance (Add SOC2/ISO 27001 compliance control evidence report #245); rebased cleanly onto dev.

[codacy-production]

Up to standards ✅

🟢 Issues 0 issues

Results:
0 new issues

View in Codacy

🟢 Metrics 47 complexity · 0 duplication

Metric	Results
Complexity	47
Duplication	0

View in Codacy

_{NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.}

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud